Search Results for author:
Found 11 papers, 5 papers with code
Weighted Ensemble Self-Supervised Learning
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning.
Extreme normalization: approximating full-data batch normalization with single examples
While batch normalization has been successful in speeding up the training of neural networks, it is not well understood.
Towards a Semantic Perceptual Image Metric
We present a full reference, perceptual image metric based on VGG-16, an artificial neural network trained on object classification.
No Fuss Distance Metric Learning using Proxies
Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized.
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples.
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network.
Ranked #4 on
Classification
on InDL
Rethinking the Inception Architecture for Computer Vision
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.
Ranked #8 on
Retinal OCT Disease Classification
on OCT2017
Batch Normalization: Accelerating Deep Network Training byReducing Internal Covariate Shift
Training Deep Neural Networks is complicated by the factthat the distribution of each layer’s inputs changes duringtraining, as the parameters of the previous layers change. This slows down the training by requiring lower learningrates and careful parameter initialization, and makes it no-toriously hard to train models with saturating nonlineari-ties.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.
Ranked #487 on
Image Classification
on ImageNet
(Number of params metric)
Scalable, High-Quality Object Detection
Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with $0. 5$ mAP for a single model and $0. 52$ mAP for an ensemble of two models.
Deep Convolutional Ranking for Multilabel Image Annotation
Multilabel image annotation is one of the most important challenges in computer vision with many real-world applications.
